Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    news-related words or terms

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to news and media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cooks
    -0.63
     arsen
    -0.62
     whisk
    -0.61
     warp
    -0.61
     runway
    -0.60
     redund
    -0.60
     certainty
    -0.60
     defenses
    -0.59
     ballpark
    -0.59
     commencement
    -0.59
    POSITIVE LOGITS
    oft
    0.86
    research
    0.80
    DragonMagazine
    0.79
    sand
    0.78
    milo
    0.78
    proxy
    0.76
    coins
    0.76
    ãĥķãĤ©
    0.75
    tenance
    0.75
    tree
    0.74
    Act Density 0.213%

    No Known Activations